Merge pull request espnet#5730 from satvik-dixit/tmp

ESPnet Recipe for ASR on the Makerere Radio Speech Corpus

egs2/README.md

@@ -109,6 +109,7 @@ See: https://espnet.github.io/espnet/espnet2_tutorial.html#recipes-using-espnet2
 | lt_speech_commands    | Lithuanian Speech Commands dataset               | LIT                  |    https://github.com/kolesov93/lt_speech_commands                                                                                                          |              |
 | m4singer                | Multi-Style, Multi-Singer and Musical Score Provided Mandarin Singing Corpus                                                                                | SVS                     | CMN                  | https://drive.google.com/file/d/1xC37E59EWRRFFLdG3aJkVqwtLDgtFNqW/view?usp=share_link                                                                               |              |
 | magicdata               | MAGICDATA Mandarin Chinese Read Speech Corpus                                                                                    | ASR                     | ENG                  | https://www.openslr.org/68/                                                                                  |              |
+| makerere               | Makerere Radio Speech Corpus                                                                                    | ASR                     | LUG                  | https://zenodo.org/records/5855017                                                                                |              |
 | media                   | MEDIA speech database for French                                                                                                 | SLU/Entity Classifi.    | FRA                  | https://catalogue.elra.info/en-us/repository/browse/ELRA-S0272/                                              |              |
 | mediaspeech             | MediaSpeech: Multilanguage ASR Benchmark and Dataset                                                                             | ASR                     | FRA                  | https://www.openslr.org/108/                                                                                 |              |
 | meld                    | MELD: Multimodal EmotionLines Dataset                                                                                            | SLU                     | ENG                  | https://affective-meld.github.io/									     |              |

egs2/makerere/asr1/README.md

@@ -0,0 +1,48 @@
+<!-- Generated by scripts/utils/show_asr_result.sh -->
+# RESULTS
+## Environments
+- date: `Thu Mar 28 00:34:47 EDT 2024`
+- python version: `3.10.13 | packaged by conda-forge | (main, Dec 23 2023, 15:36:39) [GCC 12.3.0]`
+- espnet version: `espnet 202402`
+- pytorch version: `pytorch 2.0.1`
+- Git hash: `eed7751c910977290ef9a177ea0942a0e3c2fd35`
+  - Commit date: `Mon Mar 25 18:26:50 2024 +0000`
+- HF link: https://huggingface.co/satvik-dixit/asr_makerere
+
+## exp/asr_train_asr_demo_branchformer_raw_en_bpe300_sp
+### WER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|inference_beam_size10_ctc_weight0.3_asr_model_valid.acc.ave/test|2154|30850|58.1|33.9|8.0|5.2|47.1|98.5|
+
+### CER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|inference_beam_size10_ctc_weight0.3_asr_model_valid.acc.ave/test|2154|207551|88.9|4.0|7.1|4.3|15.4|98.5|
+
+### TER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|inference_beam_size10_ctc_weight0.3_asr_model_valid.acc.ave/test|2154|83642|74.7|15.4|9.9|4.7|30.0|98.5|
+
+## exp/asr_train_asr_demo_branchformer_raw_en_bpe300_sp/inference_beam_size10_ctc_weight0.3_asr_model_valid.acc.ave
+### WER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|org/train_dev|200|2560|52.1|37.0|10.9|4.2|52.1|98.0|
+
+### CER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|org/train_dev|200|16726|85.3|4.9|9.7|4.2|18.9|98.0|
+
+### TER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|org/train_dev|200|6636|68.8|18.3|12.9|4.6|35.8|98.0|

egs2/makerere/asr1/asr.sh

@@ -0,0 +1 @@
+../../TEMPLATE/asr1/asr.sh

egs2/makerere/asr1/cmd.sh

@@ -0,0 +1,110 @@
+# ====== About run.pl, queue.pl, slurm.pl, and ssh.pl ======
+# Usage: <cmd>.pl [options] JOB=1:<nj> <log> <command...>
+# e.g.
+#   run.pl --mem 4G JOB=1:10 echo.JOB.log echo JOB
+#
+# Options:
+#   --time <time>: Limit the maximum time to execute.
+#   --mem <mem>: Limit the maximum memory usage.
+#   -–max-jobs-run <njob>: Limit the number parallel jobs. This is ignored for non-array jobs.
+#   --num-threads <ngpu>: Specify the number of CPU core.
+#   --gpu <ngpu>: Specify the number of GPU devices.
+#   --config: Change the configuration file from default.
+#
+# "JOB=1:10" is used for "array jobs" and it can control the number of parallel jobs.
+# The left string of "=", i.e. "JOB", is replaced by <N>(Nth job) in the command and the log file name,
+# e.g. "echo JOB" is changed to "echo 3" for the 3rd job and "echo 8" for 8th job respectively.
+# Note that the number must start with a positive number, so you can't use "JOB=0:10" for example.
+#
+# run.pl, queue.pl, slurm.pl, and ssh.pl have unified interface, not depending on its backend.
+# These options are mapping to specific options for each backend and
+# it is configured by "conf/queue.conf" and "conf/slurm.conf" by default.
+# If jobs failed, your configuration might be wrong for your environment.
+#
+#
+# The official documentation for run.pl, queue.pl, slurm.pl, and ssh.pl:
+#   "Parallelization in Kaldi": http://kaldi-asr.org/doc/queue.html
+# =========================================================~
+
+
+# Select the backend used by run.sh from "local", "stdout", "sge", "slurm", or "ssh"
+cmd_backend='local'
+
+# Local machine, without any Job scheduling system
+if [ "${cmd_backend}" = local ]; then
+
+    # The other usage
+    export train_cmd="run.pl"
+    # Used for "*_train.py": "--gpu" is appended optionally by run.sh
+    export cuda_cmd="run.pl"
+    # Used for "*_recog.py"
+    export decode_cmd="run.pl"
+
+# Local machine logging to stdout and log file, without any Job scheduling system
+elif [ "${cmd_backend}" = stdout ]; then
+
+    # The other usage
+    export train_cmd="stdout.pl"
+    # Used for "*_train.py": "--gpu" is appended optionally by run.sh
+    export cuda_cmd="stdout.pl"
+    # Used for "*_recog.py"
+    export decode_cmd="stdout.pl"
+
+
+# "qsub" (Sun Grid Engine, or derivation of it)
+elif [ "${cmd_backend}" = sge ]; then
+    # The default setting is written in conf/queue.conf.
+    # You must change "-q g.q" for the "queue" for your environment.
+    # To know the "queue" names, type "qhost -q"
+    # Note that to use "--gpu *", you have to setup "complex_value" for the system scheduler.
+
+    export train_cmd="queue.pl"
+    export cuda_cmd="queue.pl"
+    export decode_cmd="queue.pl"
+
+
+# "qsub" (Torque/PBS.)
+elif [ "${cmd_backend}" = pbs ]; then
+    # The default setting is written in conf/pbs.conf.
+
+    export train_cmd="pbs.pl"
+    export cuda_cmd="pbs.pl"
+    export decode_cmd="pbs.pl"
+
+
+# "sbatch" (Slurm)
+elif [ "${cmd_backend}" = slurm ]; then
+    # The default setting is written in conf/slurm.conf.
+    # You must change "-p cpu" and "-p gpu" for the "partition" for your environment.
+    # To know the "partion" names, type "sinfo".
+    # You can use "--gpu * " by default for slurm and it is interpreted as "--gres gpu:*"
+    # The devices are allocated exclusively using "${CUDA_VISIBLE_DEVICES}".
+
+    export train_cmd="slurm.pl"
+    export cuda_cmd="slurm.pl"
+    export decode_cmd="slurm.pl"
+
+elif [ "${cmd_backend}" = ssh ]; then
+    # You have to create ".queue/machines" to specify the host to execute jobs.
+    # e.g. .queue/machines
+    #   host1
+    #   host2
+    #   host3
+    # Assuming you can login them without any password, i.e. You have to set ssh keys.
+
+    export train_cmd="ssh.pl"
+    export cuda_cmd="ssh.pl"
+    export decode_cmd="ssh.pl"
+
+# This is an example of specifying several unique options in the JHU CLSP cluster setup.
+# Users can modify/add their own command options according to their cluster environments.
+elif [ "${cmd_backend}" = jhu ]; then
+
+    export train_cmd="queue.pl --mem 2G"
+    export cuda_cmd="queue-freegpu.pl --mem 2G --gpu 1 --config conf/queue.conf"
+    export decode_cmd="queue.pl --mem 4G"
+
+else
+    echo "$0: Error: Unknown cmd_backend=${cmd_backend}" 1>&2
+    return 1
+fi

egs2/makerere/asr1/conf/fbank.conf

@@ -0,0 +1,2 @@
+--sample-frequency=16000
+--num-mel-bins=80

egs2/makerere/asr1/conf/pbs.conf

@@ -0,0 +1,11 @@
+# Default configuration
+command qsub -V -v PATH -S /bin/bash
+option name=* -N $0
+option mem=* -l mem=$0
+option mem=0          # Do not add anything to qsub_opts
+option num_threads=* -l ncpus=$0
+option num_threads=1  # Do not add anything to qsub_opts
+option num_nodes=* -l nodes=$0:ppn=1
+default gpu=0
+option gpu=0
+option gpu=* -l ngpus=$0

egs2/makerere/asr1/conf/pitch.conf

@@ -0,0 +1 @@
+--sample-frequency=16000

egs2/makerere/asr1/conf/queue.conf

@@ -0,0 +1,12 @@
+# Default configuration
+command qsub -v PATH -cwd -S /bin/bash -j y -l arch=*64*
+option name=* -N $0
+option mem=* -l mem_free=$0,ram_free=$0
+option mem=0          # Do not add anything to qsub_opts
+option num_threads=* -pe smp $0
+option num_threads=1  # Do not add anything to qsub_opts
+option max_jobs_run=* -tc $0
+option num_nodes=* -pe mpi $0  # You must set this PE as allocation_rule=1
+default gpu=0
+option gpu=0
+option gpu=* -l gpu=$0 -q g.q

egs2/makerere/asr1/conf/slurm.conf

@@ -0,0 +1,14 @@
+# Default configuration
+command sbatch --export=PATH
+option name=* --job-name $0
+option time=* --time $0
+option mem=* --mem-per-cpu $0
+option mem=0
+option num_threads=* --cpus-per-task $0
+option num_threads=1 --cpus-per-task 1
+option num_nodes=* --nodes $0
+default gpu=0
+option gpu=0 -p cpu
+option gpu=* -p gpu --gres=gpu:$0 -c $0  # Recommend allocating more CPU than, or equal to the number of GPU
+# note: the --max-jobs-run option is supported as a special case
+# by slurm.pl and you don't have to handle it in the config file.

egs2/makerere/asr1/conf/train_asr_demo_branchformer.yaml

@@ -0,0 +1,63 @@
+batch_type: folded
+batch_size: 64
+accum_grad: 2    # gradient accumulation steps
+max_epoch: 100
+patience: none
+init: xavier_uniform
+best_model_criterion:  # criterion to save best models
+-   - valid
+    - acc
+    - max
+keep_nbest_models: 10  # save nbest models and average these checkpoints
+use_amp: true    # whether to use automatic mixed precision
+num_att_plot: 0  # do not save attention plots to save time in the demo
+num_workers: 2   # number of workers in dataloader
+
+encoder: transformer
+encoder_conf:
+    output_size: 256
+    attention_heads: 4
+    linear_units: 1024
+    num_blocks: 12
+    dropout_rate: 0.1
+    positional_dropout_rate: 0.1
+    attention_dropout_rate: 0.1
+    input_layer: conv2d
+    normalize_before: true
+
+decoder: transformer
+decoder_conf:
+    attention_heads: 4
+    linear_units: 1024
+    num_blocks: 6
+    dropout_rate: 0.1
+    positional_dropout_rate: 0.1
+    self_attention_dropout_rate: 0.1
+    src_attention_dropout_rate: 0.1
+
+model_conf:
+    ctc_weight: 0.3  # joint CTC/attention training
+    lsm_weight: 0.1  # label smoothing weight
+    length_normalized_loss: false
+
+optim: adam
+optim_conf:
+    lr: 0.001
+scheduler: warmuplr  # linearly increase and exponentially decrease
+scheduler_conf:
+    warmup_steps: 800
+specaug: specaug
+specaug_conf:
+    apply_time_warp: true
+    time_warp_window: 5
+    time_warp_mode: bicubic
+    apply_freq_mask: true
+    freq_mask_width_range:
+    - 0
+    - 30
+    num_freq_mask: 2
+    apply_time_mask: true
+    time_mask_width_range:
+    - 0
+    - 40
+    num_time_mask: 2

egs2/makerere/asr1/db.sh

@@ -0,0 +1 @@
+../../TEMPLATE/asr1/db.sh

egs2/makerere/asr1/local/data.sh

@@ -0,0 +1,61 @@
+#!/usr/bin/env bash
+# Set bash to 'debug' mode, it will exit on :
+# -e 'error', -u 'undefined variable', -o ... 'error in pipeline', -x 'print commands',
+set -e
+set -u
+set -o pipefail
+
+log() {
+    local fname=${BASH_SOURCE[1]##*/}
+    echo -e "$(date '+%Y-%m-%dT%H:%M:%S') (${fname}:${BASH_LINENO[0]}:${FUNCNAME[1]}) $*"
+}
+SECONDS=0
+
+stage=1
+stop_stage=100
+
+log "$0 $*"
+. utils/parse_options.sh
+
+. ./db.sh
+. ./path.sh
+. ./cmd.sh
+
+if [ $# -ne 0 ]; then
+    log "Error: No positional arguments are required."
+    exit 2
+fi
+
+if [ -z "${MAKERERE}" ]; then
+    log "Fill the value of 'makerere' of db.sh"
+    exit 1
+fi
+
+train_set="train_nodev"
+train_dev="train_dev"
+ndev_utt=200
+
+
+if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
+    log "stage 1: Data preparation"
+    mkdir -p data/{train,test}
+
+
+    # Prepare data in the Kaldi format, including three files:
+    # text, wav.scp, utt2spk
+    python3 local/data_prep.py ${MAKERERE} sph2pipe
+
+    for x in test train; do
+        for f in text wav.scp utt2spk; do
+            sort data/${x}/${f} -o data/${x}/${f}
+        done
+        utils/utt2spk_to_spk2utt.pl data/${x}/utt2spk > "data/${x}/spk2utt"
+    done
+
+    # make a dev set
+    utils/subset_data_dir.sh --first data/train "${ndev_utt}" "data/${train_dev}"
+    n=$(($(wc -l < data/train/text) - ndev_utt))
+    utils/subset_data_dir.sh --last data/train "${n}" "data/${train_set}"
+fi
+
+log "Successfully finished. [elapsed=${SECONDS}s]"

egs2/makerere/asr1/local/data_prep.py

@@ -0,0 +1,51 @@
+import csv
+import glob
+import os
+import random
+import sys
+
+if __name__ == "__main__":
+
+    if len(sys.argv) != 3:
+        print("Usage: python data_prep.py [root] [sph2pipe]")
+        sys.exit(1)
+
+    root = sys.argv[1]
+    sph2pipe = sys.argv[2]
+
+    all_audio_list = glob.glob(
+        os.path.join(root, "makerere_radio_dataset/transcribed/dataset", "*.wav")
+    )
+    random.shuffle(all_audio_list)
+
+    df = {}
+    with open(
+        "downloads/makerere_radio_dataset/transcribed/cleaned.csv", "r"
+    ) as csvfile:
+        reader = csv.reader(csvfile)
+        next(reader)
+        for row in reader:
+            df[row[0]] = row[2]
+
+    for x in ["train", "test"]:
+        if x == "train":
+            audio_list = all_audio_list[0 : int(len(all_audio_list) * 0.8)]
+        else:
+            audio_list = all_audio_list[int(len(all_audio_list) * 0.8) :]
+        # print('audio_list', len(audio_list))
+
+        with open(os.path.join("data", x, "text"), "w") as text_f, open(
+            os.path.join("data", x, "wav.scp"), "w"
+        ) as wav_scp_f, open(os.path.join("data", x, "utt2spk"), "w") as utt2spk_f:
+            i = 0
+            for audio_path in audio_list:
+                filename = os.path.basename(audio_path)
+                speaker = filename.split(".")[0][8]
+                if filename not in df or len(list(df[filename])) == 0:
+                    continue
+                transcript = df[filename]
+                uttid = filename[:-4]  # "sk-o73a"
+                wav_scp_f.write(f"{uttid} {audio_path}\n")
+                text_f.write(f"{uttid} {transcript}\n")
+                utt2spk_f.write(f"{uttid} {speaker}\n")
+                i = i + 1

egs2/makerere/asr1/path.sh

@@ -0,0 +1 @@
+../../TEMPLATE/asr1/path.sh